© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12250
    Prev
    Next
    INDEX
    Explanations

    expressions related to questioning actions and motives, especially concerning negative thoughts or decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of desire and intention, particularly in the context of questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.04
    2:0.08
    3:0.17
    4:0.02
    5:0.05
    6:0.07
    7:0.06
    8:0.13
    9:0.12
    10:0.07
    11:0.14
    Negative Logits
     penetrating
    -1.26
     preced
    -1.22
     disabling
    -1.12
     inherent
    -1.11
    eret
    -1.10
     contracting
    -1.09
    Express
    -1.09
     amplification
    -1.09
     indirect
    -1.08
     accessing
    -1.06
    POSITIVE LOGITS
     ASAP
    1.18
    venge
    1.17
    ????
    1.16
    shit
    1.11
    ppa
    1.09
    bye
    1.09
    !!!!
    1.08
    eeee
    1.08
    !!!!!!!!
    1.08
    morrow
    1.05
    Activations Density 0.012%

    No Known Activations